Data to drive the desired effect – action shots

Now would be a good time to introduce the photo effect we want to create in this chapter. The effect, as I know it, is called an action shot. It's essentially a still photograph that shows someone (or something) in motion, probably best illustrated with an image - like the one shown here: 

 

Note

As previously mentioned, the model we used in this chapter performs binary (or single-class) classification. This simplification, using a binary classifier instead of a multi-class classifier, has been driven by the intended use that is just segmenting people from the background. Similar to any software project, you should strive for simplicity where you can.

To extract people, we need a model to learn how to recognize people and their associated pixels. For this, we need a dataset consisting of images of people and corresponding images with those pixels of the persons labeled—and lots of them. Unlike datasets for classification, datasets for object segmentation...